An interactive visualization system has a receiver that receives image data corresponding to one or more biomechanical movements of a user. Further, the interactive visualization system has a processor that performs a biomechanical analysis, via a biomechanical rules engine, of the image data to determine that the one or more biomechanical movements of the user lack compliance with one or more biomechanical rules. The processor generates a virtual sports feedback cue to be rendered, in at least substantially real-time, via a virtual sports performance expert during performance of the one or more biomechanical movements of the user. Finally, the interactive visualization system has a transmitter that transmits the virtual sports feedback cue to the biomechanical data ingestion apparatus so that a rendering apparatus renders the virtual sports performance expert performing the virtual sports feedback cue in a manner visible to the user during the one or more biomechanical movements.

A plurality of motion sensors capable of capturing IR video, depth video, and RGB images. Periodically emitting IR pulses. Capturing IR video, depth video, and RGB images of a user. Generating a point cloud of the user. Generating a 3D model of the user including the point cloud of the user. Inputting the IR video, depth video, and RGB images into a machine learning model. Estimating a set of joints of the user in the 3D model. Tracking, based on the estimated set of joints of the user in the 3D model, the user's motion over a period of time. Determining a number of repetitions of an exercise performed by the user. Determining a feedback value. Calculating, based on the number of repetitions and the feedback value, a user exercise score. Providing, via a graphical user interface, the user exercise score and the feedback value to the user.

Disclosed are computer-implemented techniques for providing immediate feedback to rowers for training and other activities to improve competitiveness of rowing crews. The techniques include a computing device receiving from a set of stroke unit devices, data that represent changes in acceleration of users' seats corresponding to users' strokes, receiving reference stroke data corresponding to a reference user's stroke, and generating from the received data from the set of stroke unit devices and the received reference strokes data, feedback data that correspond to relative stroke timing differences of each of the users, relative to the reference stroke, and transmitting the generated feedback data to user devices according to a feedback mechanism. Various feedback mechanisms are disclosed including visual, audio and tactical feedback mechanisms.

Methods and systems are disclosed for pose comparison, interactive physical gaming, and remote fitness training on a user computing device. The methods and systems are configured to first receive a reference feature generated from a frame of a reference video, the reference feature computed from a reference posture of a reference person in the frame of the reference video. Next, receive a frame of a user video, the frame of the user video comprising a user. Next, extract a user posture from the frame of the user video, by performing a machine learning-based computer vision algorithm that detects one or more body key points of the user in an image plane of the user video. Finally, generate a user feature from the user posture; and determine an output score based on a distance between the reference feature and the user feature.

A system and method for using a body joystick to interact with a virtual or mixed-reality machines or software applications that uses a support arm to hold a device for attaching the body joystick to a user's body, a sensor for detecting movement, and a tether and actuator for providing feedback to the user about interactions with the virtual or mixed-reality machines or software applications.

There is disclosed a system for conducting multi-member group competitions involving physical exertion, the system includes a competition server that serves to designate a set of parameters for a competition involving at least two competing groups of individuals engaged in physical activity, the set of parameters defining a win condition requiring physical activity to be completed by at least two separate individuals within each group. The system further receives data representative of physical activity of multiple individuals in a first group, receives data representative of physical activity of multiple individuals in a second group, determines whether the win condition has been satisfied by the first group or the second group, and identifies a winner as the first group or the second group that completed the win condition.

[Object] More efficient evaluation of the motions of multiple users is made possible. [Solving Means] An information processing apparatus is provided that includes a motion estimation section configured to analyze data recorded of motions of multiple users so as to estimate the motions, a tag addition section configured to add tag data regarding the motions to at least part of the recorded data, and a motion evaluation section configured to evaluate the motions by comparing the motions with reference motions on the basis of the tag data.

A knee rehabilitation system includes a plurality of compressible resistance members, a knee garment, and a resistance member receptacle. Each compressible resistance member in the plurality of compressible resistance members has (i) a same size and a shape as each other compressible resistance member in the plurality of compressible resistance members, and (ii) a compression resistance different from each other compressible resistance member in the plurality of compressible resistance members. The knee garment has a knee garment ventral portion and a knee garment dorsal portion. The resistance member receptacle is coupled to the knee garment dorsal portion, and the resistance member receptacle is sized to carry each compressible resistance member in the plurality of compressible resistance members, one at a time.

This disclosure relates to method and system for training users to perform physical activities. The method includes capturing real-time video of the user performing the activity based on an activity option selected by the user; extracting an AI model based on the activity option; processing in real-time, by the AI model, the real-time video of the user to determine a set of user performance parameters based on current activity performance of the user; overlaying, by the AI model, the user in the real-time video with a pose skeletal model; comparing, by the AI model, the set of user performance parameters with a set of target activity performance parameters; generating, by the AI model, feedback for the user based on comparison of the set of user performance parameters with the set of target activity performance parameters; and rendering, by the AI model, the feedback on the rendering device.

The disclosure relates to system and method for Artificial Intelligence (AI) assisted activity training. The method includes presenting a plurality of activity categories to a user and receiving a voice-based input from the user. The method uses a Natural Language Processing (NLP) model to process the received voice-based input to extract the selection of at least one activity and at least one activity attribute. Contemporaneous to receiving voice-based input, the method presents a multimedia content in conformance with one activity and one activity attribute. In response to initiation of the multimedia content, the method further detects initiation of a user activity performance. The method captures a video of the user activity and process the video using an AI model to extract a set of user performance parameters. Further, a feedback may be generated based on differential between the set of user performance parameters and a target set of performance parameters.